Neural Belief Tracker: Data-Driven Dialogue State Tracking
This addresses the problem of scaling belief tracking in spoken dialogue systems for developers, though it is incremental as it builds on existing representation learning methods.
The paper tackles the scalability issues in dialogue state tracking by proposing a Neural Belief Tracking (NBT) framework that uses pre-trained word vectors, achieving performance matching state-of-the-art models with hand-crafted lexicons and outperforming them without such lexicons.
One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user's goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users' language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided.